Convert Docx for Office 365.

convertToDocx365.rb

require "fileutils"

# Version 3.1
#
# Description: This script solves the problem when opening docx files with the new office 360. Some documents report "Xml parsing error"
# This is due to an deprecated xml tag. This script parses the docx and removes them.
#
# Requires 7zip installed and added to the path.
#
# usage:
#       ruby convertToDocx365 file.docx
#
# This will generate a converted docx file
# Remember to open the docx and refresh the index table
# @ToDo replace 7zip and use a gem to compres the file.


# Begin:
# requires a xml filename as parameter to replace its content
module ConvertToDocx365
    def self.Convert file_name
        puts "file to open : #{file_name}"
        # required to match preserve and preserver
        match_patern    = /xml:space="preserv(er"|e")/

        text = File.read(file_name)
        text.gsub!(match_patern, "" )

        # To write changes to the file, use:
        File.open(file_name, "w") {|file| file.puts text }
        puts "matches were replaced OK"
        return true
    end
    def self.run( cmd )
    	puts cmd
    	system cmd
    end
end

puts "Convertions begins:"
docx_file   = ARGV[0]
if( docx_file.index(' ') != nil)
    puts "the file name contains spaces"
    abort
end
target_doc  = 'document.xml'
target_dir  = "#{docx_file}_temp"
puts (File.basename docx_file)

puts "extracting #{target_doc}"

#   x = extract using folder structure
#  -r = recursive
# -oc = output folder
CMD_UNZIP = "7z x #{docx_file} -oc:#{target_dir} -r"
ConvertToDocx365::run CMD_UNZIP

puts "Replacing paterns"
res = ConvertToDocx365::Convert File.join( '.', target_dir, 'word', target_doc)

if res then
    # rename the original file to "old"
    CMD_MOVE  = "mv #{docx_file} #{docx_file}.old"
    ConvertToDocx365::run CMD_MOVE
    #   a = add to zip
    CMD_ZIP   = "7z a #{docx_file} .\\#{target_dir}\\* -r"
    ConvertToDocx365::run CMD_ZIP
    puts "Done"
else
    puts "Failed"
end